This is the home of a collaborative data collection effort by U. Chicago and TTI-Chicago researchers. This is to our knowledge the first collection of American Sign Language fingerspelling data "in the wild," that is in naturally occurring (online) video.
The ChicagoFSWild data set contains 7304 ASL fingerspelling sequences signed by 160 signers, carefully annotated by students who have studied ASL.
Variants: ChicagoFSWild
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Sign Language Recognition | HandReader_RGB_KP | HandReader: Advanced Techniques for Efficient … | 2025-05-15 |
| Sign Language Recognition | HandReader_KP | HandReader: Advanced Techniques for Efficient … | 2025-05-15 |
| Sign Language Recognition | HandReader_RGB | HandReader: Advanced Techniques for Efficient … | 2025-05-15 |
Recent papers with results on this dataset: